INDEX

Explanations

non

np_acts-logits-general · gemini-2.5-flash-lite

The main thing this neuron does is detect numeric date expressions (years, full dates, and their punctuation).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

punctuation marks and formatting characters, particularly colons, commas, periods, hyphens, and whitespace in structured text.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 देखील

1.33

 सुद्धा

1.30

हरु

1.30

無い

1.27

 diatas

1.22

の為

1.21

が無い

1.20

 dibawah

1.18

 الغير

1.18

出来る

1.17

POSITIVE LOGITS

—

1.13

.—

0.93

FIGURE

0.91

 FIGURE

0.90

 toward

0.89

 nong

0.88

Toward

0.88

 CHAPTER

0.83

 Toward

0.80

—“

0.80

Activations Density 0.549%

non

The main thing this neuron does is detect numeric date expressions (years, full dates, and their punctuation).

punctuation marks and formatting characters, particularly colons, commas, periods, hyphens, and whitespace in structured text.

No Comments

No Known Activations

non

The main thing this neuron does is detect numeric date expressions (years, full dates, and their punctuation).

punctuation marks and formatting characters, particularly colons, commas, periods, hyphens, and whitespace in structured text.

No Comments

No Known Activations